{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DE56JLLHLHVYAVUG6QEYI3LLFV","short_pith_number":"pith:DE56JLLH","schema_version":"1.0","canonical_sha256":"193be4ad6759eb805686f409846d6b2d793a85650b2d02dffabea2a30639bba8","source":{"kind":"arxiv","id":"2506.18385","version":1},"attestation_state":"computed","paper":{"title":"InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Botian Shi, Haomin Wang, Hongjie Zhang, Jifeng Dai, Kaipeng Zhang, Lixin Gu, Min Dou, Nianchen Deng, Shenglong Ye, Songze Li, Tianshuo Yang, Tong He, Wenhai Wang, Wenqi Shao, Xingguang Wei, Yanting Zhang, Yinan He, Yi Wang, Yu Qiao, Zhe Chen","submitted_at":"2025-06-23T08:17:22Z","abstract_excerpt":"Recent benchmarks and datasets have been proposed to improve spatial reasoning in vision-language models (VLMs), yet existing open resources remain limited in scale, visual diversity, and instruction expressiveness. In this work, we introduce InternSpatial, the largest open-source dataset for spatial reasoning in VLMs, along with InternSpatial-Bench, a corresponding evaluation benchmark designed to assess spatial understanding under diverse instruction formats. InternSpatial comprises 12 million QA pairs spanning both single-view and multi-view settings, drawn from diverse visual environments "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.18385","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T08:17:22Z","cross_cats_sorted":[],"title_canon_sha256":"7d5be393917df850dd6b40f3ee3eaa4ccdb3258b481ea3d72536f522140efc51","abstract_canon_sha256":"a6284bd3aa306d268c58c79aa7fd64072da26ae7b06782fc15125c5e49eafa65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:49.534382Z","signature_b64":"n+qg7pTJeQmLezTxMg8zDycCyhi9RxCly2wUe81wDwT/FRtx9MA30LUBsPpgOF3hr5gV7kKNepsk5L78HqnaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"193be4ad6759eb805686f409846d6b2d793a85650b2d02dffabea2a30639bba8","last_reissued_at":"2026-07-05T11:25:49.533882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:49.533882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Botian Shi, Haomin Wang, Hongjie Zhang, Jifeng Dai, Kaipeng Zhang, Lixin Gu, Min Dou, Nianchen Deng, Shenglong Ye, Songze Li, Tianshuo Yang, Tong He, Wenhai Wang, Wenqi Shao, Xingguang Wei, Yanting Zhang, Yinan He, Yi Wang, Yu Qiao, Zhe Chen","submitted_at":"2025-06-23T08:17:22Z","abstract_excerpt":"Recent benchmarks and datasets have been proposed to improve spatial reasoning in vision-language models (VLMs), yet existing open resources remain limited in scale, visual diversity, and instruction expressiveness. In this work, we introduce InternSpatial, the largest open-source dataset for spatial reasoning in VLMs, along with InternSpatial-Bench, a corresponding evaluation benchmark designed to assess spatial understanding under diverse instruction formats. InternSpatial comprises 12 million QA pairs spanning both single-view and multi-view settings, drawn from diverse visual environments "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18385","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.18385/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.18385","created_at":"2026-07-05T11:25:49.533942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18385v1","created_at":"2026-07-05T11:25:49.533942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18385","created_at":"2026-07-05T11:25:49.533942+00:00"},{"alias_kind":"pith_short_12","alias_value":"DE56JLLHLHVY","created_at":"2026-07-05T11:25:49.533942+00:00"},{"alias_kind":"pith_short_16","alias_value":"DE56JLLHLHVYAVUG","created_at":"2026-07-05T11:25:49.533942+00:00"},{"alias_kind":"pith_short_8","alias_value":"DE56JLLH","created_at":"2026-07-05T11:25:49.533942+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08952","citing_title":"AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20448","citing_title":"Do Vision-Language Models Understand 3D Scenes or Just Catalogue Objects?","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22536","citing_title":"SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22536","citing_title":"SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20448","citing_title":"Do Vision-Language Models Understand 3D Scenes or Just Catalogue Objects?","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03944","citing_title":"SCP: Spatial Causal Prediction in Video","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11462","citing_title":"SpatialForge: Bootstrapping 3D-Aware Spatial Reasoning from Open-World 2D Images","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02913","citing_title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DE56JLLHLHVYAVUG6QEYI3LLFV","json":"https://pith.science/pith/DE56JLLHLHVYAVUG6QEYI3LLFV.json","graph_json":"https://pith.science/api/pith-number/DE56JLLHLHVYAVUG6QEYI3LLFV/graph.json","events_json":"https://pith.science/api/pith-number/DE56JLLHLHVYAVUG6QEYI3LLFV/events.json","paper":"https://pith.science/paper/DE56JLLH"},"agent_actions":{"view_html":"https://pith.science/pith/DE56JLLHLHVYAVUG6QEYI3LLFV","download_json":"https://pith.science/pith/DE56JLLHLHVYAVUG6QEYI3LLFV.json","view_paper":"https://pith.science/paper/DE56JLLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18385&json=true","fetch_graph":"https://pith.science/api/pith-number/DE56JLLHLHVYAVUG6QEYI3LLFV/graph.json","fetch_events":"https://pith.science/api/pith-number/DE56JLLHLHVYAVUG6QEYI3LLFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DE56JLLHLHVYAVUG6QEYI3LLFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DE56JLLHLHVYAVUG6QEYI3LLFV/action/storage_attestation","attest_author":"https://pith.science/pith/DE56JLLHLHVYAVUG6QEYI3LLFV/action/author_attestation","sign_citation":"https://pith.science/pith/DE56JLLHLHVYAVUG6QEYI3LLFV/action/citation_signature","submit_replication":"https://pith.science/pith/DE56JLLHLHVYAVUG6QEYI3LLFV/action/replication_record"}},"created_at":"2026-07-05T11:25:49.533942+00:00","updated_at":"2026-07-05T11:25:49.533942+00:00"}